论文标题
一种基于模型的SAT方法，用于枚举
A Model-Agnostic SAT-based Approach for Symbolic Explanation Enumeration
论文作者
论文摘要
在本文中，题为“基于模型的SAT”方法，用于列举符号解释，我们提出了一种通用的不可知论方法，允许生成不同和互补类型的符号解释。更确切地说，我们通过分析特征与输出之间的关系来生成解释以局部解释单个预测。我们的方法使用预测模型的命题编码和基于SAT的设置来生成两种类型的符号解释，这是足够的原因和反事实。图像分类任务的实验结果表明了所提出的方法的可行性及其在提供充分的原因和反事实解释方面的有效性。
In this paper titled A Model-Agnostic SAT-based approach for Symbolic Explanation Enumeration we propose a generic agnostic approach allowing to generate different and complementary types of symbolic explanations. More precisely, we generate explanations to locally explain a single prediction by analyzing the relationship between the features and the output. Our approach uses a propositional encoding of the predictive model and a SAT-based setting to generate two types of symbolic explanations which are Sufficient Reasons and Counterfactuals. The experimental results on image classification task show the feasibility of the proposed approach and its effectiveness in providing Sufficient Reasons and Counterfactuals explanations.
